We aim to achieve compositional and hierarchical action modeling and reasoning from video inputs in the context of computer vision.
***STUDENTS WITH EXPERIENCE IN COMPUTER VISION AND ML ONLY. Please answer the following question when registering for the project: What are your experience with computer vision and machine learning?***Please see the PDF for a detailed project description. When registering for this project in UniTime, look for 'Merck (Computer Vision)' in the Note section, and select the appropriate CRN.